Method and apparatus for assessing a physiological signal quality based on an IABP device

Abstract

The present disclosure provides a method and an apparatus for assessing a physiological signal quality based on an IABP device, and relates to the technical field of medical instruments. The method includes: acquiring, in the operation process of an IABP device, physiological signal of a patient treated by the IABP device, where the physiological signal include an electrocardiographic signal and/or an arterial blood pressure signal; extracting signal parameter values of the physiological signal, where the signal parameter values include: a first kurtosis, a skewness, an effective signal ratio, a second kurtosis, and a dominant frequency; performing signal quality assessment on the physiological signal based on the signal parameter values; and implementing, based on the physiological signal, intra-aortic balloon counterpulsation in response to a signal quality assessment result represents that the signal quality of the physiological signal satisfies a preset signal quality requirement.

What is claimed is: 
     
         1 . A method for assessing a physiological signal quality based on an Intra-Aortic Balloon counterPulsation (IABP) device, comprising:
 acquiring, in an operation process of the IABP device, a physiological signal of a patient treated by the IABP device, wherein the physiological signal comprises an electrocardiographic signal and/or an arterial blood pressure signal;   extracting signal parameter values of the physiological signal;   wherein the signal parameter values comprise: a first kurtosis, a skewness, an effective signal ratio, a second kurtosis, and a dominant frequency, the first kurtosis represents a steepness or a flatness of the physiological signal in a time domain distribution, the skewness represents a direction and a degree of deflection of the physiological signal in the time domain distribution, the effective signal ratio represents a ratio of an effective component relative to a total component in the physiological signal, the second kurtosis represents a steepness or a flatness of the physiological signal in a frequency domain distribution, and the dominant frequency represents a frequency corresponding to the second kurtosis of the physiological signal in the frequency domain distribution;   performing signal quality assessment on the physiological signal based on the signal parameter values;   in response to a signal quality assessment result represents that a signal quality of the physiological signal satisfies a preset signal quality requirement, implementing intra-aortic balloon counterpulsation based on the physiological signal.   
     
     
         2 . The method as claimed in  claim 1 , wherein performing signal quality assessment on the physiological signal based on the signal parameter value comprises:
 extracting a signal feature of the signal parameter values;   performing feature fusion on the extracted signal feature to obtain a target feature;   performing signal quality classification on the physiological signal based on the target feature to obtain the signal quality assessment result.   
     
     
         3 . The method as claimed in  claim 2 , wherein performing signal quality classification on the physiological signal based on the target feature comprises:
 inputting the target feature into a pre-trained support vector machine model to obtain a signal quality classification result output by the support vector machine model, which serves as the signal quality assessment result, wherein the support vector machine model is a model obtained by training, by adopting a support vector machine algorithm and a Gaussian radial basis function, an initial support vector machine model with signal parameter values of sample physiological signals as training samples and actual signal quality results of the sample physiological signals as training standards, and the support vector machine model is configured to perform signal quality classification on the physiological signal.   
     
     
         4 . The method as claimed in  claim 3 , wherein when the physiological signal is electrocardiographic signal, the signal parameter values further comprise: the number of R waves in the electrocardiographic signal and the dispersion of RR intervals, the dispersion of RR intervals represents the dispersion of the time intervals between two adjacent R waves in the electrocardiographic signal, and the effective signal ratio comprises a first-category effective signal ratio and a second-category effective signal ratio. 
     
     
         5 . The method as claimed in  claim 2 , wherein when the physiological signal is an electrocardiographic signal, the signal parameter value further comprises: the number of R waves in the electrocardiographic signal and a dispersion of RR intervals, the dispersion of RR intervals represents a dispersion of time intervals between two adjacent R waves in the electrocardiographic signal, and the effective signal ratio comprises a first-category effective signal ratio and a second-category effective signal ratio. 
     
     
         6 . The method as claimed in  claim 1 , wherein performing signal quality assessment on the physiological signal based on the signal parameter value comprises:
 judging whether the dominant frequency is within a preset dominant frequency range, wherein the preset dominant frequency range is a normal dominant frequency range corresponding to a signal type of the physiological signal;   in response to the dominant frequency being within the preset dominant frequency range, determining a target quantity of signal parameter values, within corresponding preset target signal parameter ranges, from target signal parameter values, and performing signal quality assessment on the physiological signal based on the target quantity, wherein the target signal parameter values comprise the first kurtosis, the skewness, the effective signal ratio, and the second kurtosis, and the preset target signal parameter ranges are normal signal parameter value ranges corresponding to a signal type of the physiological signal.   
     
     
         7 . The method as claimed in  claim 6 , wherein performing signal quality assessment on the physiological signal based on the target quantity comprises:
 determining, from various preset quantity ranges, a target quantity range within which the target quantity falls, wherein the various preset quantity ranges correspond to preset signal quality grades;   adopting a preset signal quality grade corresponding to the target quantity range as the signal quality assessment result for the physiological signal.   
     
     
         8 . The method as claimed in  claim 1 , wherein acquiring, in the operation process of the IABP device, the physiological signal of the patient treated by the IABP device comprises:
 acquiring a signal sampling rate;   acquiring the physiological signal of the patient treated by the IABP device based on the signal sampling rate.   
     
     
         9 . The method as claimed in  claim 1 , wherein extracting the signal parameter values of the physiological signal comprises:
 calculating the first kurtosis and the skewness based on a length of the physiological signal, a signal value of the physiological signal, a mean value of the physiological signal and a variance of the physiological signal;   performing fast Fourier transform (FFT) on the physiological signal to obtain power spectral density (PSD) of the physiological signal;   obtaining the effective signal ratio, the second kurtosis, and the dominant frequency based on the power spectral density.   
     
     
         10 . The method as claimed in  claim 1 , wherein performing signal quality assessment on the physiological signal based on the signal parameter values comprises:
 extracting a signal feature of the signal parameter values;   obtaining a matching degree by matching signal features corresponding to the physiological signal with a preset signal quality with the signal feature of the signal parameter values;   obtaining the signal quality assessment result based on the matching degree.   
     
     
         11 . The method as claimed in  claim 1 , wherein obtaining the matching degree by matching signal features corresponding to the physiological signal with the preset signal quality with the signal feature of the signal parameter values comprises:
 calculating a distance between the signal feature of the signal parameter values and the signal features corresponding to the physiological signal with the preset signal quality;   obtaining the matching degree based on the distance.   
     
     
         12 . An apparatus for assessing a physiological signal quality based on an Intra-Aortic Balloon counterPulsation (IABP) device, comprising:
 a signal acquisition module, configured to acquire, in an operation process of the IABP device, physiological signal of a patient treated by the IABP device, wherein the physiological signal comprises an electrocardiographic signal and/or an arterial blood pressure signal;   a data extraction module, configured to extract signal parameter values of the physiological signal, wherein the signal parameter values comprise a first kurtosis, a skewness, an effective signal ratio, a second kurtosis, and a dominant frequency, the first kurtosis represents a steepness or a flatness of the physiological signal in a time domain distribution, the skewness represents a direction and a degree of deflection of the physiological signal in the time domain distribution, the effective signal ratio represents a ratio of an effective component relative to a total component in the physiological signal, the second kurtosis represents a steepness or a flatness of the physiological signal in a frequency domain distribution, and the dominant frequency represents a frequency corresponding to the second kurtosis of the physiological signal in the frequency domain distribution;   a signal quality assessment module, configured to perform signal quality assessment on the physiological signal based on the signal parameter values;   a balloon counterpulsation module, configured to implement, based on the physiological signal, intra-aortic balloon counterpulsation in response to a signal quality assessment result represents that a signal quality of the physiological signal satisfies a preset signal quality requirement.   
     
     
         13 . The apparatus as claimed in  claim 12 , wherein the signal quality assessment module comprises:
 a feature extraction sub-module, configured to an extract signal feature of the signal parameter values;   a feature fusion sub-module, configured to perform feature fusion on the extracted signal feature to obtain a target feature;   a first signal quality assessment sub-module, configured to perform signal quality classification on the physiological signal based on the target feature to obtain the signal quality assessment result.   
     
     
         14 . The apparatus as claimed in  claim 13 , wherein the first signal quality assessment sub-module is configured to input the target feature into a pre-trained support vector machine model to obtain a signal quality classification result output by the support vector machine model, which serves as the signal quality assessment result, wherein the support vector machine model is a model obtained by training, by adopting a support vector machine algorithm and a Gaussian radial basis function, an initial support vector machine model with signal parameter values of sample physiological signals as training samples and actual signal quality results of the sample physiological signals as training standards, and the support vector machine model is configured to perform signal quality classification on the physiological signal. 
     
     
         15 . The apparatus as claimed in  claim 14 , wherein when the physiological signal is electrocardiographic signal, the signal parameter values further comprise: the number of R waves in the electrocardiographic signal and the dispersion of RR intervals, the dispersion of RR intervals represents the dispersion of the time intervals between two adjacent R waves in the electrocardiographic signal, and the effective signal ratio comprises a first-category effective signal ratio and a second-category effective signal ratio. 
     
     
         16 . The apparatus as claimed in  claim 13 , wherein when the physiological signal is an electrocardiographic signal, the signal parameter values further comprise: the number of R waves in the electrocardiographic signal and a dispersion of RR intervals, the dispersion of RR intervals represents the dispersion of time intervals between two adjacent R waves in the electrocardiographic signal, and the effective signal ratio comprises a first-category effective signal ratio and a second-category effective signal ratio.